Abstract: Fitting a model to a collection of observations is one of the quintessential problems in machine learning. Since any model is only approximately valid, an estimator that is useful in practice must also be robust in the presence of model misspecification. It turns out that there is a striking tension between robustness and computational efficiency. Even for the most basic high-dimensional tasks, until recently the only known estimators were either hard to compute or could only tolerate a negligible fraction of errors.
In this talk, I will describe the first robust and efficiently computable estimators for several fundamental learning tasks that were previously thought to be computationally intractable. These include robust estimation of mean and covariance in high dimensions, robust learning of various latent variable models, and robust stochastic optimization. The new robust estimators are scalable in practice and have a number of applications in exploratory data analysis and adversarial machine learning.
Bio: Ilias Diakonikolas is an Assistant Professor and Andrew and Erna Viterbi Early Career Chair in the Department of Computer Science at USC. He obtained a Diploma in electrical and computer engineering from the National Technical University of Athens and a Ph.D. in computer science from Columbia University where he was advised by Mihalis Yannakakis. Before moving to USC, he was a faculty member at the University of Edinburgh, and prior to that he was the Simons postdoctoral fellow in theoretical computer science at the University of California, Berkeley. His research is on the algorithmic foundations of massive data sets, in particular on designing efficient algorithms for fundamental problems in machine learning. He is a recipient of a Sloan Fellowship, an NSF CAREER Award, a Google Faculty Research Award, a Marie Curie Fellowship, the IBM Research Pat Goldberg Best Paper Award, and an honorable mention in the George Nicholson competition from the INFORMS society.